© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3396
    Prev
    Next
    INDEX
    Explanations

    mentions of database related things

    oai_token-act-pair · gemini-2.0-flash

    administrative terms

    np_token-act-pair-logits · gpt-4o-mini

    administration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.68
    SPATH
    -0.58
    AutoScale
    -0.56
    DoubleQuotes
    -0.55
    Cursors
    -0.54
    redients
    -0.53
    tramp
    -0.53
    bootstrapcdn
    -0.50
    helves
    -0.50
    cierto
    -0.49
    POSITIVE LOGITS
    TypedDataSet
    0.70
     admin
    0.68
     administ
    0.68
     administrators
    0.68
     administrator
    0.67
     administration
    0.65
     Admin
    0.63
    Cyfeiriadau
    0.63
     Administ
    0.62
     admins
    0.61
    Activations Density 3.006%

    No Known Activations